Classification of Remotely Sensed Images using Artificial Neural Networks

Remote Sensing (RS) image classification has recently attracted great attention for its application in different tasks, including environmental monitoring, battlefield surveillance, and geospatial object detection. The best practices for these tasks often involve transfer learning from pre-trained Convolutional Neural Networks (CNNs). A common approach in the literature is employing CNNs for feature extraction, and subsequently train classifiers exploiting such features. In this paper, we propose the adoption of transfer learning by fine-tuning pre-trained CNNs for end-to-end aerial image classification. Our approach performs feature extraction from the fine-tuned neural networks and remote sensing image classification with a Support Vector Machine (SVM) model with linear and Radial Basis Function (RBF) kernels. To tune the learning rate hyperparameter, we employ a linear decay learning rate scheduler as well as cyclical learning rates. Moreover, in order to mitigate the overfitting problem of pre-trained models, we apply label smoothing regularization. For the fine-tuning and feature extraction process, we adopt the Inception-v3 and Xception inception-based CNNs, as well the residual-based networks ResNet50 and DenseNet121. We present extensive experiments on two real-world remote sensing image datasets: AID and NWPU-RESISC45. The results show that the proposed method exhibits classification accuracy of up to 98%, outperforming other state-of-the-art methods.

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

Abstract: The classification of images can be influenced by various factors. When multiple sources of data are available for earth exploration, extracting valuable information or achieving effective outcomes can be both fascinating and challenging. Remote Sensing Images (RSI) classification plays a crucial role in remote sensing applications and serves as the foundation for efficient classification. Various classifiers are employed to classify different types of targets in remote sensing images. Achieving improved target classification is of utmost importance in both military and civilian domains. This paper focuses on summarizing advanced approaches used to enhance classification accuracy. The findings indicate that the Convolutional Neural Network surpasses all other conventional classification methods.

Price movement predictions of financial instruments using traditional time-series models with a predefined mathematical structure are common, but this method restricts their ability to learn latent patterns in the data. In recent times, artificial neural networks (ANN) have been able to learn complex hidden patterns from financial datasets using a highly nonlinear architecture. However, most experiments with neural networks require a lot of time to search a suitable network and subsequently train the network. The authors have developed a deep multilayer perceptron (MLP) classifier with a zero-centered piecewise linear unit activation that yielded better classification performance according to their accuracy metric and required consistently less training time compared to a similar MLP network with leaky rectified linear unit and tanh activation functions. The authors illustrate their technique with a large high-frequency dataset on selected bank shares from the Indian stock market. The authors also discuss the theoretical properties and advantages of their proposal. <b>TOPICS:</b>Statistical methods, simulations, big data/machine learning <b>Key Findings</b> • Time-series models have been used extensively to understand stock price movements. They are constrained by a predefined structure. Artificial neural network (ANNs), due to their universal approximation properties, offer more flexibility; however, they suffer from long training times. • In this article, the authors introduce a zero-centered piecewise linear unit (PLU), a hybrid activation function derived from tanh and leaky rectified linear unit (ReLU) functions that exhibits the zero-centered property from tanh and the nonzero gradient property from leaky ReLU. • The authors developed a multilayer perceptron (MLP) classifier with PLU activation, which yielded better classification performance according to the accuracy metric and required consistently less training time compared to a similar MLP network with leaky ReLU and tanh activation.

Ecological Applications of Fuzzy Logic.- Ecological Applications of Qualitative Reasoning.- Ecological Applications of Non-supervised Artificial Neural Networks.- Ecological Applications of Genetic Algorithms.- Ecological Applications of Evolutionary Computation.- Ecological Applications of Adaptive Agents.- Bio-Inspired Design of Computer Hardware by Self-Replicating Cellular Automata.- Prediction and Elucidation of Stream Ecosystems.- Development and Application of Predictive River Ecosystem Models Based on Classification Trees and Artificial Neural Networks.- Modelling Ecological Interrelations in Running Water Ecosystems with Artificial Neural Networks.- Non-linear Approach to Grouping, Dynamics and Organizational Informatics of Benthic Macroinvertebrate Communities in Streams by Artificial Neural Networks.- Elucidation of Hypothetical Relationships between Habitat Conditions and Macroinvertebrate Assemblages in Freshwater Streams by Artificial Neural Networks.- Prediction and Elucidation of River Ecosystems.- Prediction and Elucidation of Population Dynamics of the Blue-green Algae Microcystis aeruginosa and the Diatom Stephanodiscus hantzschii in the Nakdong River-Reservoir System (South Korea) by a Recurrent Artificial Neural Network.- An Evaluation of Methods for the Selection of Inputs for an Artificial Neural Network Based River Model.- Utility of Sensitivity Analysis by Artificial Neural Network Models to Study Patterns of Endemic Fish Species.- Prediction and Elucidation of Lake and Marine Ecosystems.- A Comparison between Neural Network Based and Multiple Regression Models for Chlorophyll-a Estimation.- Artificial Neural Network Approach to Unravel and Forecast Algal Population Dynamics of Two Lakes Different in Morphometry and Eutrophication.- Hybrid Evolutionary Algorithm for Rule Set Discovery in Time-Series Data to Forecast and Explain Algal Population Dynamics in Two Lakes Different in Morphometry and Eutrophication.- Multivariate Time Series Prediction of Marine Zooplankton by Artificial Neural Networks.- Classification of Fish Stock-Recruitment Relationships in Different Environmental Regimes by Fuzzy Logic with Bootstrap Re-sampling Approach.- Computational Assemblage of Ordinary Differential Equations for Chlorophyll-a Using a Lake Process Equation Library and Measured Data of Lake Kasumigaura.- Classification of Ecological Images at Micro and Macro Scale.- Identification of Marine Microalgae by Neural Network Analysis of Simple Descriptors of Flow Cytometric Pulse Shapes.- Age Estimation of Fish Using a Probabilistic Neural Network.- Pattern Recognition and Classification of Remotely Sensed Images by Artificial Neural Networks.

Multipoint milling tool supervision using artificial neural network approach

Accuracy of land cover classification in remotely sensed images relies on the features extracted and the classifier used. Texture features are significant in land cover classification. Traditional texture models capture only patterns with discrete boundaries whereas fuzzy patterns need to be classified by assigning due weightage to uncertainty. When remotely sensed image contains noise, the image may have fuzzy patterns characterizing land covers and fuzzy boundaries separating land covers. So a fuzzy texture model is proposed for effective classification of land covers in remotely sensed images and the model uses Sugeno Fuzzy Inference System (FIS). Support Vector Machine (SVM) is used for precise and fast classification of image pixels. Hence it is proposed to use a hybrid of fuzzy texture model and SVM for land cover classification of remotely sensed images. In this chapter, land cover classification of IRS-P6, LISS-IV remotely sensed image is performed using multivariate version of the proposed texture model.

The spatial distribution characteristics of remote sensing scene imagery exhibit significant complexity, necessitating the extraction of critical semantic features and effective discrimination of feature information to improve classification accuracy. While the combination of traditional convolutional neural networks (CNNs) and Transformers has proven effective in extracting features from both local and global perspectives, the multilayer perceptron (MLP) within Transformers struggles with nonlinear problems and insufficient feature representation, leading to suboptimal performance in fused models. To address these limitations, we propose a Swin Kansformer network for remote sensing scene classification, which integrates the Kolmogorov–Arnold Network (KAN) and employs a window-based self-attention mechanism for global information extraction. By replacing the traditional MLP layer with the KAN module, the network approximates functions through the decomposition of complex multivariate functions into univariate functions, enhancing the extraction of complex features. Additionally, an asymmetric convolution group module is introduced to replace conventional convolutions, further improving local feature extraction capabilities. Experimental validation on the AID and NWPU-RESISC45 datasets demonstrates that the proposed method achieves classification accuracies of 97.78% and 94.90%, respectively, outperforming state-of-the-art models such as ViT + LCA and ViT + PA by 0.89%, 1.06%, 0.27%, and 0.66%. These results highlight the performance advantages of the Swin Kansformer, while the incorporation of the KAN offers a novel and promising approach for remote sensing scene classification tasks with broad application potential.

Traditional machine learning (ML) techniques are often employed to perform complex pattern recognition tasks for remote sensing images, such as land-use classification. In order to obtain acceptable classification results, these techniques require there to be sufficient training data available for every particular image. Obtaining training samples is challenging, particularly for near real-time applications. Therefore, past knowledge must be utilized to overcome the lack of training data in the current regime. This challenge is known as domain adaptation (DA), and one of the common approaches to this problem is based on finding invariant representations for both the training and test data, which are often assumed to come from different “domains.” In this study, we consider two deep learning techniques for learning domain-invariant representations: Denoising autoencoders (DAE) and domain-adversarial neural networks (DANN). While the DAE is a typical two-stage DA technique (unsupervised invariant representation learning followed by supervised classification), DANN is an end-to-end approach where invariant representation learning and classification are considered jointly during training. The proposed techniques are applied to both hyperspectral and multispectral images under different DA scenarios. Results obtained show that the proposed techniques outperform traditional approaches, such as principal component analysis (PCA) and kernel PCA, and can also compete with a fully supervised model in the multispatial scenario.

Neural network has been increasingly used in remote sensing image classification in the last few decades. Nevertheless, an efficient method for high resolution remote sensing image classification, particularly panchromatic (PAN) image, is still under investigation. This work presents a neural network classification method for urban land cover mapping using the wavelet-based features extracted from a PAN IKONOS image. A structured-based neural network with back propagation through structure (BPTS) algorithm is conducted for image classification. After wavelet decomposition, the object's contents from the PAN image can be represented by its wavelet coefficients. The pixels' spectral intensity and the derived wavelet coefficients are combined as attributes for the tree representation in the neural network. With the designed neural network structure, a total of 2510 pixels of four land cover classes are selected as training data and 19498 pixels for the same land cover classes are selected for testing data. All the land cover classes are perfectly classified (100%) using the selected training data and the classification rate based on testing data set reaches to 99.68%. The experimental results reveal that the proposed method demonstrates a viable solution for classification of high resolution panchromatic remote sensing data.

With the growing demand for better performance of remote sensing (RS) image classification, a variety of methods have been proposed in RS image classification field in recent years. In general, there are two categories of RS image classification methods: pixel-based (PB) approach and object-based (OB) approach. In this paper, RS image classification methods are reviewed from the perspective of PB approach and OB approach and, specifically, the development and characteristics of a promising methodology for RS image classification named support vector machine (SVM) are surveyed. SVM is particularly popular in the RS field since it can deal with small-sized training dataset and provide higher classification accuracy than some traditional methods like maximum likelihood classifier. Besides, SVM has advantages of high memory-efficiency and strong generalization. However, SVM-based approaches also suffer from some problems. For instance, SVM-based methods tend to overfit due to inappropriate choice of kernel functions and it is inefficient for them to determine the optimum kernel function parameters as well as to process hyperspectral images. This paper also proposes the improvement of SVM-based methods aiming to address the limitations and improve the performance of SVM in RS image classification field. Moreover, future directions for SVM in RS image classification field are presented, expecting to help researchers to find possible research focuses in the future.

Land-use information provides a direct representation of the effect of human activities on the environment, and an accurate and efficient land-use classification of remote sensing images is an important element of land-use and land-cover change research. To solve the problems associated with traditional land-use classification methods (e.g., rapid increase in dimensionality of data, inadequate feature extraction, and low running efficiency), a method that combines object-oriented approach with deep convolutional neural network (COCNN) is presented. First, a multi-scale segmentation algorithm is used to segment images to generate image segmentation regions with high homogeneity. Second, a typical rule set of feature objects is constructed on the basis of the object-oriented segmentation results, and the segmentation objects are classified and extracted to form a training sample set. Third, a convolutional neural network (CNN) model structure is modified to improve classification performance, and the training algorithm is optimized to avoid the overfitting phenomenon that occurs during training using small datasets. Ten land-use types are classified by using the remote sensing images covering the area around Fuxian Lake as an example. By comparing the COCNN method with the method based solely on CNN, precision and kappa index were selected to evaluate the classification accuracy of the two methods. For the COCNN method, on the basis of the classification statistics, precision and kappa index coefficients are 96.2% and 0.96, respectively, which are 8.98% and 0.1 higher than those of the method based solely on CNN. Experimental results show that the COCNN method reasonably and efficiently combines object-oriented and deep learning approaches, thereby effectively solving the problem of the inaccurate classification of typical features with better classification accuracy than the simple use of CNN.

Remote sensing image classification is a prerequisite for remote sensing applications, such as thematic mapping, urban planning, forest management, environment monitoring, disaster warning and assessment, military target recognition. Over the last decade there has been noticeable shift in remote sensing image classification with the extension of remote sensing imagery sources as well as the development of pattern recognition methods. This paper discusses the changes in remote sensing classification from two aspects: basic thought and new classification algorithms. The basic thought of remote sensing classification has changed from per-pixel multispectral-based approaches to multiscale object-based approaches. New classification algorithms include support vector machine, evolutionary algorithm, fuzzy clustering algorithm, as well as Artificial Neural Networks. At last this paper highlights the future research and application directions of remote sensing image classification.

Remote Sensing (RS) image classification, particularly involving Earth Observation (EO) satellite data, presents significant challenges due to the complexity and variety of image content. This study addresses these challenges by evaluating the performance of three advanced deep learning models—DenseNet121, ResNet50, and EfficientNetB7—on the UC Merced Land Use (UCM) dataset. By leveraging pre-trained Convolutional Neural Networks (CNNs) through transfer learning, our approach effectively mitigates the issue of limited labelled data and enhances the accuracy of classification in high-resolution aerial imagery. This paper provides an in-depth study of said models, emphasizing their accuracy, precision, recall, and computing efficiency in the classification of land use domains. The findings provide insightful information about how well these various CNN architectures perform in classifying remote sensing images and lay the groundwork for further deep learning-based land use categorization research

The difficulties of tuning parameters of multilayer perceptrons (MLP) classifiers are well known. In this paper, a measure is described that is capable of predicting the number of classifier training epochs for achieving optimal performance in an ensemble of MLP classifiers. The measure is computed between pairs of patterns on the training data and is based on a spectral representation of a Boolean function. This representation characterizes the mapping from classifier decisions to target label and allows accuracy and diversity to be incorporated within a single measure. Results on many benchmark problems, including the Olivetti Research Laboratory (ORL) face database demonstrate that the measure is well correlated with base-classifier test error, and may be used to predict the optimal number of training epochs. While correlation with ensemble test error is not quite as strong, it is shown in this paper that the measure may be used to predict number of epochs for optimal ensemble performance. Although the technique is only applicable to two-class problems, it is extended here to multiclass through output coding. For the output-coding technique, a random code matrix is shown to give better performance than one-per-class code, even when the base classifier is well-tuned.